AI Paper Atlas

Research map / Video / Action recognition

HAA500: Human-Centric Atomic Action Dataset With Curated Videos

Jihoon Chung, Cheng-hsin Wuu, Hsuan-ru Yang, Yu-Wing Tai, Chi-Keung Tang

ICCV 2021 · Video › Action recognition · approach: Disentangled action recognition · 47 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add atomic action labels to composite labels in training (ablation)I3D RGB · HAA500 Instrument composite classificationtop-1 accuracy: 70.59% -> 71.90%Improved
add atomic action labels to composite labels in training (ablation)I3D RGB · HAA500 Sport composite classificationtop-1 accuracy: 47.48% -> 53.93%Improved
add atomic action labels to composite labels in training (ablation)TSN RGB · HAA500 Sport composite classificationtop-1 accuracy: 72.64% -> 72.48%Hurt
add pose input to RGB (ablation)I3D · HAA500top-1 accuracy: 33.53% -> 42.80%Improved
add pose input to RGB (ablation)I3D · Gym288top-1 accuracy: 76.11% -> 77.31%Improved
pre-train on HAA500 instead of no pre-trainingI3D-RGB · UCF101 fine-tuningtop-1 accuracy: 58.87% -> 68.70%Improved
pre-train on HAA500 instead of no pre-trainingI3D-RGB · HMDB51 fine-tuningtop-1 accuracy: 28.56% -> 40.45%Improved
pre-train on AVA instead of no pre-trainingI3D-RGB · UCF101 fine-tuningtop-1 accuracy: 58.87% -> 48.54%Hurt
use relaxed (loosely trimmed) clips instead of precise temporal annotation (ablation)HAA500 · HAA500 testtop-1 accuracy: 33.53% -> 22.80%Hurt
use relaxed HAA500 for pre-training (ablation)I3D-RGB · UCF101 fine-tuningtop-1 accuracy: 68.70% -> 62.24%Hurt
normalize frames by cropping person-of-interest (ablation)I3D-RGB · HAA500 Instrument composite classificationtop-1 accuracy: 66.01% -> 75.82%Improved
add object detection heatmap channels to RGB (ablation)I3D-RGB · HAA500top-1 accuracy: 33.53% -> 33.73%No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy